Three-dimensional molecule generation by denoising voxel grids

Abstract

A voxelized representation of an input molecule may be updated by applying a molecule design computation model that has been trained to approximate a data distribution of molecules exhibiting one or more desired properties. The molecule design computation model may update the voxelized representation of the input molecule to increase a likelihood of a resultant updated voxelized representation being in the data distribution. A voxelized representation of an output molecule may be generated based on the updated voxelized representation. For example, where the molecule design computation model has been trained to approximate a noisy data distribution populated by noisy voxelized representations of the molecules exhibiting the one or more desired properties, the voxelized representation of the output molecule may be generated by denoising the updated voxelized representation in order to map the updated voxelized representation from the noisy data distribution to the true data distribution.

What is claimed is: 
     
         1 . A system for identifying a molecule having one or more desired properties, the system comprising:
 at least one data processor; and   at least one memory storing instructions, which when executed by the at least one data processor, result in operations comprising:
 generating a voxelized representation of an input molecule; 
 applying a molecule design computation model to generate an updated voxelized representation of the input molecule by at least updating the voxelized representation of the input molecule,
 where the molecule design computation model has been trained to approximate a data distribution of molecules exhibiting the one or more desired properties, 
 where the molecule design computation model updates the voxelized representation of the input molecule to increase a likelihood of the updated voxelized representation being within the data distribution, 
 where the molecule design computation model is trained by at least applying the molecule design computation model to operate on a corrupted voxelized representation of a sample molecule exhibiting the one or more desired properties, and 
 where the training includes applying the molecule design computation model to recover, from the corrupted voxelized representation of the sample molecule, an uncorrupted voxelized representation of the sample molecule; and 
 
 generating, based at least on the updated voxelized representation, a voxelized representation of an output molecule. 
   
     
     
         2 . The system of  claim 1 , wherein a voxelized representation of the input molecule includes a plurality of voxels organized into a three-dimensional voxel grid, and wherein each atom in the input molecule is represented as a continuous density across one or more voxels in the three-dimensional voxel grid. 
     
     
         3 . The system of  claim 2 , wherein the continuous density of each atom in the input molecule is centered at a center of each atom, and wherein a first voxel that is distanced from any atoms in the input molecule is associated with a lower atomic density value than a second voxel proximate to the center of an atom in the input molecule. 
     
     
         4 . The method of any of  claims 2 to 3 , wherein each voxel in the three-dimensional voxel grid is associated with a value indicative of an atomic density at a corresponding location. 
     
     
         5 . The system of  claim 1 , wherein the voxelized representation of the input molecule includes one or more channels, and wherein each channel corresponds to a type of atom present in the input molecule. 
     
     
         6 . The system of  claim 1 , wherein the voxelized representation of the input molecule jointly represents a type and a position of one or more atoms present in the input molecule. 
     
     
         7 . The system of  claim 1 , wherein applying the molecule design computation model to update the voxelized representation of the input molecule comprises updating the voxelized representation of the input molecule based at least on a function that outputs a value indicative of a likelihood of the resultant updated voxelized representation within the data distribution. 
     
     
         8 . The system of  claim 7 , wherein the operations further comprise:
 parameterizing the function using a plurality of parameters of the molecule design computation model.   
     
     
         9 . The system of  claim 7 , wherein the function comprises a score function, and wherein the value output by the function includes a score indicating a local change in a density of the data distribution at a location of the updated voxelized representation. 
     
     
         10 . The system of  claim 1 , wherein the molecule design computation model updates the voxelized representation of the input molecule by at least
 updating the voxelized representation of the input molecule thereby generating a first updated voxelized representation,   updating the voxelized representation of the input molecule thereby generating a second updated voxelized representation,   applying a function parameterized by the molecule design computation model to determine a first value indicative of a first local change in a density of the data distribution at a first location occupied by the first updated voxelized representation,   applying the function to determine a second value indicative of a second local change in the density of the data distribution at a second location occupied by the second updated voxelized representation, and   further updating, when the first value and the second value are indicative of a higher density of the data distribution at the first location than at the second location, the first updated voxelized representation instead of the second updated voxelized representation.   
     
     
         11 . The system of  claim 10 , wherein the molecule design computation model is applied to further update the first updated voxelized representation until one or more criteria are met. 
     
     
         12 . The system of  claim 11 , wherein the one or more criteria include at least one of (i) performing a threshold quantity of iterations of updates to the voxelized representation of the input molecule, (ii) the first value of the first updated voxelized representation satisfying one or more thresholds, and (iii) generating a threshold quantity of output molecules. 
     
     
         13 . The system of  claim 10 , wherein the molecule design computation model is applied to further modify the first updated voxelized representation instead of the second updated voxelized representation based at least on the first value and the second value indicating that the first updated voxelized representation has a higher likelihood within the data distribution than the second updated voxelized representation. 
     
     
         14 . The system of  claim 10 , wherein the molecule design computation model is applied to further modify the first updated voxelized representation instead of the second updated voxelized representation based at least on the first value and the second value indicating that the first updated voxelized representation is sampled from a higher density region of the data distribution than the second updated voxelized representation. 
     
     
         15 . The system of  claim 1 , wherein the data distribution is a noisy data distribution populated by noisy voxelized representations of the molecules exhibiting the one or more desired properties, and wherein the voxelized representation of the output molecule is generated by denoising the first updated voxelized representation in order to map the first updated voxelized representation from the noisy data distribution to a true data distribution of the molecules exhibiting the one or more desired properties. 
     
     
         16 . The system of  claim 1 , wherein the operations further comprise:
 translating the voxelized representation of the output molecule into a different representation of the output molecule.   
     
     
         17 . The system of  claim 16 , wherein the different representation of the output molecule includes a one-dimensional representation of the output molecule and/or a two-dimensional representation of the output molecule. 
     
     
         18 . The system of  claim 16 , wherein the voxelized representation of the output molecule is translated by at least
 determining a position of one or more atoms in the output molecule by at least detecting one or more peaks in a plurality of atomic density values comprised in the voxelized representation of the output molecule, and   determining, based at least the positions of the one or more atoms, one or more interconnecting bonds.   
     
     
         19 . A computer-implemented method, comprising:
 generating a voxelized representation of an input molecule;   applying a molecule design computation model to generate an updated voxelized representation of the input molecule by at least updating the voxelized representation of the input molecule,
 where the molecule design computation model has been trained to approximate a data distribution of molecules exhibiting the one or more desired properties, 
 where the molecule design computation model updates the voxelized representation of the input molecule to increase a likelihood of the updated voxelized representation being within the data distribution, 
 where the molecule design computation model is trained by at least applying the molecule design computation model to operate on a corrupted voxelized representation of a sample molecule exhibiting the one or more desired properties, and 
 where the training includes applying the molecule design computation model to recover, from the corrupted voxelized representation of the sample molecule, a voxelized representation of the sample molecule; and 
   generating, based at least on the updated voxelized representation, a voxelized representation of an output molecule.   
     
     
         20 . A non-transitory computer readable medium storing instructions, which when executed by at least one data processor, result in operations comprising:
 generating a voxelized representation of an input molecule;   applying a molecule design computation model to generate an updated voxelized representation of the input molecule by at least updating the voxelized representation of the input molecule,
 where the molecule design computation model has been trained to approximate a data distribution of molecules exhibiting the one or more desired properties, 
 where the molecule design computation model updates the voxelized representation of the input molecule to increase a likelihood of the updated voxelized representation being within the data distribution, 
 where the molecule design computation model is trained by at least applying the molecule design computation model to operate on a corrupted voxelized representation of a sample molecule exhibiting the one or more desired properties, and 
 where the training includes applying the molecule design computation model to recover, from the corrupted voxelized representation of the sample molecule, a voxelized representation of the sample molecule; and 
   
       generating, based at least on the updated voxelized representation, a voxelized representation of an output molecule. 
     
     
         21 . The system of  claim 1 , wherein the training of the molecule design computation model includes:
 identifying the sample molecule;   generating a noisy voxelized representation of the sample molecule;   adding noise to the noisy voxelized representation of the sample molecule to generate a corrupted voxelized representation of the sample molecule; and   training a molecule design computation model to approximate the data distribution of molecules exhibiting the one or more desired properties by at least applying the molecule design computation model to recover the noisy voxelized representation of the sample molecule from the corrupted voxelized representation of the sample molecule.   
     
     
         22 . (canceled) 
     
     
         23 . (canceled) 
     
     
         24 . (canceled) 
     
     
         25 . (canceled) 
     
     
         26 . (canceled) 
     
     
         27 . (canceled) 
     
     
         28 . The system of  claim 1 , wherein the training of the molecule design computation model includes adjusting a plurality of parameters of the molecule design computation model to reduce a difference between the uncorrupted voxelized representation of the sample molecule generated by the molecule design computation model and the noisy voxelized representation of the sample molecule. 
     
     
         29 . The system of  claim 28 , wherein the plurality of parameters of the molecule design computation model parameterize a function, and wherein the values of the plurality of parameters are adjusted such that the function outputs a value indicative of a local change in a density of the data distribution of molecules exhibiting the one or more desired properties. 
     
     
         30 . The system of  claim 1 , wherein the molecule design computation model generates the updated voxelized representation of the input molecule by at least updating an atomic density of one or more voxels in at least one channel of the voxelized representation of the input molecule. 
     
     
         31 . The system of  claim 30 , wherein the updating of the atomic density of the one or more voxels in the at least one channel of the voxelized representation of the input molecule corresponds to updating at least one of a type and/or a position of one or more atoms present in the input molecule. 
     
     
         32 . The system of  claim 1 , wherein the molecule design computation model updates the voxelized representation of the input molecule over multiple iterations of gradient based Markov Chain Monte Carlo (MCMC) sampling until one or more criteria are satisfied. 
     
     
         33 . The system of  claim 32 , wherein the one or more criteria include at least one of (i) performing a threshold quantity of iterations of gradient-based Markov Chain Monte Carlo (MCMC) sampling, (ii) sampling the voxelized representation of the output molecule from a region having a threshold density, and (iii) generating a threshold quantity of output molecules. 
     
     
         34 . (canceled) 
     
     
         35 . (canceled) 
     
     
         36 . (canceled) 
     
     
         37 . (canceled) 
     
     
         38 . The system of  claim 1 , wherein the training of the molecule design computation model includes
 applying the molecule design computation model having a first adjustment to denoise the corrupted voxelized representation of the sample molecule and generate a first recovered voxelized representation of the sample molecule,   determining a first mean squared error (MSE), quantifying a first difference between the first recovered voxelized representation and the noisy voxelized representation of the sample molecule,   applying the molecule design computation model having a second adjustment to denoise the corrupted voxelized representation of the sample molecule and generate a second recovered voxelized representation of the sample molecule,   determining second first mean squared error (MSE), quantifying a second difference between the second recovered voxelized representation and the noisy voxelized representation of the sample molecule, and   upon determining that the first mean squared error (MSE) is less than the second mean squared error (MSE), further adjusting the molecule design computation model having the first adjustment instead of the second adjustment.   
     
     
         39 . (canceled) 
     
     
         40 . (canceled) 
     
     
         41 . The system of  claim 1 , wherein the one or more desired properties include at least one of affinity, specificity, biological activity, and developability. 
     
     
         42 . The system of  claim 1 , wherein the updating the voxelized representation of the input molecule includes removing at least a portion of noise present in the voxelized representation of the input molecule.